Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    server-side encryption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    airs
    0.41
    ANC
    0.40
    ESSMENT
    0.40
    맥
    0.38
     encounters
    0.38
    Anders
    0.38
     embeds
    0.37
    andum
    0.36
    ystone
    0.36
     বিদ্রোহীদের
    0.35
    POSITIVE LOGITS
     krzy
    0.43
     Ahí
    0.42
     arz
    0.39
     Körper
    0.39
     disfraz
    0.38
     dout
    0.38
     ကု
    0.37
    胱
    0.37
     lichaam
    0.37
     Aí
    0.37
    Act Density 0.000%

    No Known Activations